✕ Clear all filters
8 articles
▶ Videos →

📰 Dev.to · Thomas Landgraf

8 articles · Updated every 3 hours · View all reads

All Articles 113,178Blog Posts 122,632Tech Tutorials 28,892Research Papers 23,285News 16,818 ⚡ AI Lessons
Claude Code Workflows: The Plan Moves Out of Claude's Head and Into a Script You Can Edit
Dev.to · Thomas Landgraf 🤖 AI Agents & Automation ⚡ AI Lesson 1mo ago
Claude Code Workflows: The Plan Moves Out of Claude's Head and Into a Script You Can Edit
Subagents, skills, and agent teams all keep the plan in one place: Claude's head. Claude decides,...
View lesson → + Playlist
I Gave 13 LLMs the Same Codebase and Asked for a Specification. Six Ran on My Laptop.
Dev.to · Thomas Landgraf 🧠 Large Language Models ⚡ AI Lesson 1mo ago
I Gave 13 LLMs the Same Codebase and Asked for a Specification. Six Ran on My Laptop.
There are benchmarks for code an LLM writes. HumanEval, MBPP, SWE-Bench, LiveCodeBench. There are no...
View lesson → + Playlist
I Didn't Ship an 'Improve My Spec' Button. I Shipped Two.
Dev.to · Thomas Landgraf 📋 Product Management ⚡ AI Lesson 1mo ago
I Didn't Ship an 'Improve My Spec' Button. I Shipped Two.
For most of its life, the tool I maintain was good at one half of the job: keeping specifications...
View lesson → + Playlist
Why I Shipped Two Artifact Mechanisms In My VS Code Extension — Not One
Dev.to · Thomas Landgraf ⚡ AI Lesson 1mo ago
Why I Shipped Two Artifact Mechanisms In My VS Code Extension — Not One
A specification is more than text. It comes with a wireframe, the regulatory PDF it answers to, the...
View lesson → + Playlist
The Window Is Closing: Spend $1200 on Yourself Before AI Pricing Catches Up
Dev.to · Thomas Landgraf 📰 AI News & Updates ⚡ AI Lesson 2mo ago
The Window Is Closing: Spend $1200 on Yourself Before AI Pricing Catches Up
The developers who use the current cheap-access era to become AI-native will keep accelerating when...
View lesson → + Playlist
The SDK You Pick Matters More Than the Model — A 13-LLM Benchmark on the Same Agentic Task
Dev.to · Thomas Landgraf 🧠 Large Language Models ⚡ AI Lesson 2mo ago
The SDK You Pick Matters More Than the Model — A 13-LLM Benchmark on the Same Agentic Task
If you have ever built an agent that walks a codebase, calls tools, and writes structured output, you...
View lesson → + Playlist
Four failure modes you'll hit running a local LLM in a multi-step agentic loop
Dev.to · Thomas Landgraf 🧠 Large Language Models ⚡ AI Lesson 2mo ago
Four failure modes you'll hit running a local LLM in a multi-step agentic loop
Most local-LLM benchmarks measure single-turn chat quality. Agentic workflows are a different beast:...
View lesson → + Playlist
Your PO Should Own the Spec, Not the Developer — Here's How Status Gates Fix the AI Handoff Problem
Dev.to · Thomas Landgraf 🤖 AI Agents & Automation ⚡ AI Lesson 3mo ago
Your PO Should Own the Spec, Not the Developer — Here's How Status Gates Fix the AI Handoff Problem
In most AI-assisted workflows, the developer writes the prompt and owns the outcome. The Product...
View lesson → + Playlist